Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Plural words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detach
    -0.07
    .StatusCode
    -0.07
    _hat
    -0.07
     prepend
    -0.06
    decoder
    -0.06
    ibold
    -0.06
     bindings
    -0.06
    .getLongitude
    -0.06
    .attrib
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     Fairy
    0.08
     Elves
    0.08
     fairy
    0.07
    maids
    0.07
    mi
    0.07
     survives
    0.06
     inference
    0.06
    ateur
    0.06
    .FR
    0.06
     illustrating
    0.06
    Act Density 0.005%

    No Known Activations